Closed mikiihuang closed 5 years ago
Hi @mikiihuang.
ppl
means perplexity and gN
means gradient norm.Cheers!
Hi @mikiihuang.
ppl
means perplexity andgN
means gradient norm.- How long did you train the model? It is normal to start with a low BLEU score. In the papers, we reported the elapsed runtime of our experiments.
Cheers!
Thank you very much!! Actually I didn't run it for a long time due to the memory issue.However the work you did really inspires me 👍Cheers.
thanks for your excellent work in the interesting issue. When i'm training with your given monument_300 data,I saw the output like this:
step 4100 lr 1 step-time 2.35s wps 2.36K ppl 64.10 gN 3.08 bleu 2.74, Sat Dec 8 14:28:50 2018
Can you tell me what does the ppl and gN mean? And why is the BLEU score so small? Thank you very much.